ClawHub
Back to skill

Security audit

Qingflow

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Qingflow connector that can read and change Qingflow business data through the oo CLI, with explicit confirmation rules for write and destructive actions.

Install this only if you want an agent to access your connected Qingflow workspace. Review write and rollback requests carefully before approving them, because those actions can modify business records or workflow state.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger description is extremely broad: it instructs the agent to use this skill for ANY Qingflow request, including read, create, update, and delete operations. That can cause unintended invocation in loosely related contexts and route sensitive or state-changing tasks through this connector without sufficient task-specific gating, increasing the chance of unintended data access or modification.

Static analysis

No suspicious patterns detected.